happyxtt's repositories
CNNs_SLFP_quantization
8-bit Small Logarithmic floating-point (SLFP) and Small floating point (SFP) CNN quantization and retraining (fine-tuning) based on max-scaling.
Language:Python000
SLFP-mixed-precision-PTQ-of-MobileNet
8-bit small log floating-point quantization was verified using CUDA C
Language:Cuda000